Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only/idempotent/closed-world, so the 'Read-only' sentence is largely redundant. However the description adds real behavioral value beyond the annotations: the error semantics for an unknown slug and the warning that the payload is a full markdown write-up (i.e. potentially large). No pagination or size guidance, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no filler, front-loaded with the return contents before the invocation requirement. Every sentence carries distinct information (what it returns, what it needs, what happens on error).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the full burden of describing return values, and it does so field by field. Combined with the slug prerequisite and error behavior, an agent has everything needed to invoke this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema alone would justify a baseline 3. The description adds provenance semantics the schema does not: the slug must come from list_case_studies and invalid values are recoverable. The optional 'intent' parameter is left to the schema, which documents it thoroughly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb (Returns) and a specific resource (one GingerLive campaign case study), then enumerates the returned fields (title, date, URL, full markdown write-up with brand/approach/results). The word 'one' plus the slug requirement cleanly separates it from the sibling list_case_studies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the prerequisite path ('Requires a slug from list_case_studies') and routes the agent to that sibling for discovery. It also states the failure mode ('an unknown slug returns the list of valid slugs'), so the agent knows both when to call this and what happens if it guesses wrong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and determinism profile is covered. The description adds genuinely new context beyond that: the data is a 'static snapshot of gingerlive.io's public facts', telling the agent results are cached/public and not live. It stops short of noting response verbosity or shape, but with annotations carrying the safety burden this is solid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the resource and its contents, then routing guidance, then a behavioral footnote. Every clause is functional, though the parenthetical platform list and partner/contact enumeration make it denser than strictly necessary for selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by enumerating what the response contains (profile, platforms, stats, partners, links) plus its static/public nature. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and there is a single optional 'intent' parameter fully documented in the schema, including what not to include (personal data). The description adds nothing about the parameter, so the baseline of 3 applies — the schema does all the work here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Returns) and resource (GingerLive's company profile) and enumerates the concrete contents: platform description, supported streaming platforms, network stats, measurement partners, contact links. It explicitly names the siblings it is not (get_network_stats, list_ad_formats, get_streamer_program_info), so an agent can distinguish it without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger condition ('Use first for general "what is GingerLive" questions') and pairs each alternative use case with its dedicated sibling tool. Nothing about when to pick this over the others is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds provenance context ('GingerLive's published network numbers'), which tells the agent these are static published figures rather than live data — a useful behavioral detail beyond the annotations, though it doesn't cover freshness or caching.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly packed sentences: the first front-loads what is returned, the second handles routing and read-only status. Every clause earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although there is no output schema, the description enumerates the returned figures precisely, and annotations cover the safety profile. An agent has everything needed to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one optional parameter with 100% schema description coverage, so the schema already documents 'intent' fully. The description adds nothing about it, which is the expected baseline when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Returns GingerLive's network reach and performance figures') and enumerates the exact metrics returned (streamer count, unique reach, hours watched, view-through rate). This clearly separates it from sibling tools like list_case_studies or get_company_overview.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ('when a user asks about scale or performance benchmarks') and names the alternative for the adjacent case ('use list_case_studies for campaign-specific results'). Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/destructive=false, so the safety profile is covered. The description still adds useful context beyond annotations: the tool returns public program information and that the ad program is in-stream. It does not cover scope limitations or return format, but with annotations carrying the safety burden this is solid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with what is returned, followed by routing guidance and a safety note. No waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only informational tool with no output schema and a fully documented optional param, the description covers purpose, usage, and routing. Minor gap: it doesn't hint at the shape of the returned info (e.g., plans or program tiers), but nothing critical is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single optional 'intent' param at 100% schema coverage, so the schema already explains it. The description needn't add param detail, and it correctly adds nothing redundant.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: returns how livestreamers join and earn with GingerLive, and enumerates the returned content (cost, ad program, platforms, sign-up link). This distinguishes it from generic company/stat tools and from the sibling list_ad_formats it explicitly routes away from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use ('creator or streamer monetization questions') and names two alternatives with their own selection condition ('for brand-side questions use get_company_overview or list_ad_formats'). No inference required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered and the trailing 'Read-only' is largely redundant. The description does add value by disclosing what the response contains (a short description per format plus badges like unskippable and adblock-safe), though it says nothing about result size, pagination, or caching.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the resource and its contents, then the routing rule; three sentences with no filler. The parenthetical example list is somewhat long but earns its place by making the formats concrete for comparison tasks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-required-param list tool with no output schema, the description covers purpose, contents, usage, and the sibling alternative, which is close to sufficient. The only gap is that the single optional 'intent' parameter and any auth/prerequisite context go unmentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

One optional parameter with 100% schema description coverage, so the schema already explains the 'intent' hint fully. The description never mentions the parameter or that it is optional telemetry-only, so it adds nothing beyond the structured field; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (lists) and resource (livestream ad formats GingerLive sells), and enumerates concrete examples (picture-in-picture, banners, pinned chat drops) so an agent knows exactly what domain this covers. It also names what each item carries (short description, badges), distinguishing it from the sibling overview tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ('planning or comparing ad formats') and routes the agent to the correct alternative ('use get_company_overview for the company itself'), which is the key ambiguity given the sibling set of company/case-study tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only' in the description is redundant reinforcement. The description does usefully disclose the return shape, but says nothing about result volume, pagination, or filtering limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with what it returns, then routing, then a one-word safety tag. No filler text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly compensates by naming the fields returned, and the next-step routing completes the picture. Minor gaps remain around list size or pagination, but nothing needed to invoke the tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the single 'intent' parameter is fully documented in the schema itself. The description adds no meaning about this parameter (e.g. that it is telemetry-only and never filters results), so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Lists GingerLive campaign case studies') and enumerates the returned fields (slug, title, excerpt, URL). An agent can immediately distinguish it from get_case_study, which returns the full write-up.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ('to find proof points or results for a brand, category or format') and names the follow-up alternative with the condition that selects it ('then call get_case_study with a slug'). The routing chain is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.